Explore

Generated with davisbrown/flux-half-illustration

Fine-tune FLUX

Customize FLUX.1 [dev] with Ostris's AI Toolkit on Replicate. Train the model to recognize and generate new concepts using a small set of example images, for specific styles, characters, or objects. (Generated with davisbrown/flux-half-illustration.)

I want to…

Make videos with Wan2.1

Generate videos with Wan2.1, the fastest and highest quality open-source video generation model.

Restore images

Models that improve or restore images by deblurring, colorization, and removing noise

Enhance videos

Models that enhance videos with super-resolution, sound effects, motion capture and other useful production effects.

Detect objects

Models that detect or segment objects in images and videos.

Make 3D stuff

Models that generate 3D objects, scenes, radiance fields, textures and multi-views.

Use FLUX fine-tunes

Browse the diverse range of fine-tunes the community has custom-trained on Replicate

Control image generation

Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.

Latest models

Dia 1.6B by Nari Labs, Generates realistic dialogue audio from text, including non-verbal cues and voice cloning

Updated 748 runs

hunyuan3d-2 optimised with the pruna toolkit: https://github.com/PrunaAI/pruna

Updated 505 runs

fofr/color-matcher

Color match and white balance fixes for images

Updated 368 runs

Updated 747 runs

Updated 2.5K runs

Fine-tune GR00T-N1 from Nvidia on a LeRobot dataset

Updated 261 runs

Updated 216 runs

Updated 21.7K runs

Image Inpainting with Flux.1-dev + ControlNet, by Alimama Team, **BETA** version

Updated 22 runs

Another face swap model? 🧐 Yep, but with indexes. Swap exactly the faces you want by picking their positions. Simple, flexible, and works great on group photos.

Updated 786 runs

TinyClick: Single-Turn Agent for Empowering GUI Automation

Updated 17 runs

This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.

Updated 4.8K runs

Updated 363 runs

Classifies text with fine tuned BERT. The model handles batched input texts in a single API call to improve performance and reduce costs.

Updated 32 runs

This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!

Updated 75K runs

Make images in Studio Ghibli art style

Updated 449 runs

Vietnamese F5-TTS. Released by EraX-AI team

Updated 70 runs

Tencent Instant Character

Updated 282 runs

Updated 14 runs

Ghiblify your image with Flux EasyControl integration

Updated 1.5K runs

Lipsync model using MuseTalk

Updated 3.1K runs

Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

Updated 8.2K runs

This is an optimised version of the hidream-full model using the pruna ai optimisation toolkit!

Updated 6K runs

This is an optimised version of the hidream-l1-dev model using the pruna ai optimisation toolkit!

Updated 19.4K runs

Social Media Comment Analysis

Updated 110 runs

Updated 42 runs

ibm-granite/granite-3.3-8b-instruct

Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.

Updated 9.8K runs

The model transforms real-life image to Ghibli Style Art Images.

Updated 1.5K runs

WAI-NSFW-illustrious-SDXL v.90

Updated 6 runs

Updated 52 runs

flux dev

Updated 93.2K runs

update the official flux-redux-dev to support lora.

Updated 109 runs

DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths.

Updated 14 runs

Spanish and English Text to Speech model from Canopy Labs (3b-es_it-ft-research_release)

Updated 51 runs

Updated 4.3K runs

GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.

Updated 4.1K runs

Updated 7 runs

Updated 6.8K runs

This model is an optimised version of stable-diffusion by stability AI that is 3x faster and 3x cheaper.

Updated 159 runs

An optimized version of sdxl-lightning from Bytedance that is more than 2x faster and 2x cheaper

Updated 27 runs

This is an optimised version of the flux schnell model from black forest labs with the pruna tool. We achieve a ~3x speedup over the original model with minimal quality loss.

Updated 7.5K runs

This a pruna optimised version of the flux 1.dev model.

Updated 33.7K runs

Updated 58 runs

meta/llama-4-maverick-instruct

A 17 billion parameter model with 128 experts

Updated 57.4K runs

meta/llama-4-scout-instruct

A 17 billion parameter model with 16 experts

Updated 85.2K runs

Mediapipe Blendshape Labeler - Predicts the blend shapes of an image.

Updated 205 runs

Fast FLUX DEV -> Flux Controlnet Canny, Controlnet Depth , Controlnet Line Art, Controlnet Upscaler - You can use just one controlnet or All - LORAs: HyperFlex LoRA , Add Details LoRA , Realism LoRA

Updated 131.5K runs